{"id":"https://openalex.org/W1520370180","doi":"https://doi.org/10.21437/interspeech.2004-439","title":"A first step towards text-independent voice conversion","display_name":"A first step towards text-independent voice conversion","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1520370180","doi":"https://doi.org/10.21437/interspeech.2004-439","mag":"1520370180"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-439","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112145013","display_name":"David Suendermann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Suendermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061781359","display_name":"Harald H\u00f6ege","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harald Hoege","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1173","last_page":"1176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719534635543823},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.7238900661468506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.687357485294342},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.642568051815033},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5289754271507263},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4203363060951233},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4172844886779785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39701274037361145},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09734266996383667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719534635543823},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.7238900661468506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.687357485294342},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.642568051815033},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5289754271507263},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4203363060951233},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4172844886779785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39701274037361145},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09734266996383667},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-439","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W23142961","https://openalex.org/W129217914","https://openalex.org/W1496562625","https://openalex.org/W1538607601","https://openalex.org/W1583154192","https://openalex.org/W2111550316"],"related_works":["https://openalex.org/W254868496","https://openalex.org/W2073905179","https://openalex.org/W2928432034","https://openalex.org/W4200277070","https://openalex.org/W1989331194","https://openalex.org/W4300740495","https://openalex.org/W1969398023","https://openalex.org/W2323643941","https://openalex.org/W1998822346","https://openalex.org/W2079383297"],"abstract_inverted_index":{"So":[0],"far,":[1],"all":[2],"conventional":[3],"voice":[4,57],"conversion":[5,58],"approaches":[6],"are":[7,70],"text-dependent,":[8],"i.e.,":[9],"they":[10],"need":[11],"equivalent":[12],"training":[13,44],"utterances":[14],"of":[15,48,55,64],"source":[16],"and":[17],"target":[18],"speaker.":[19],"Since":[20],"several":[21,78],"recently":[22],"proposed":[23],"applications":[24],"call":[25],"for":[26],"renouncing":[27],"this":[28,31,49],"requirement,":[29],"in":[30],"paper,":[32],"we":[33],"present":[34],"an":[35],"algorithm":[36,50],"which":[37],"finds":[38],"corresponding":[39],"time":[40],"frames":[41],"within":[42],"text-independent":[43],"data.":[45],"The":[46],"performance":[47],"is":[51],"tested":[52],"by":[53],"means":[54],"a":[56,73],"framework":[59],"based":[60],"on":[61,72],"linear":[62],"transformation":[63],"the":[65],"spectral":[66],"envelope.":[67],"Experimental":[68],"results":[69],"reported":[71],"Spanish":[74],"cross-gender":[75],"corpus":[76],"utilizing":[77],"objective":[79],"error":[80],"measures.":[81]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
